Implementation of Optimal Weights Initialization Technology in Robot Learning

XIAO Wei; ZHOU Dong-hui; SUN Jian-feng; XU Zhi-qiang

您当前的位置：

首页 >

文章列表页 >

Implementation of Optimal Weights Initialization Technology in Robot Learning

更新时间：2025-07-16

- Implementation of Optimal Weights Initialization Technology in Robot Learning
- Acta Electronica Sinica Vol. 33, Issue 9, Pages: 1720-1722(2005)
- 作者机构：
  
  中国海洋大学电子系,山东,青岛,266071
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP24
- Published：2005
- 稿件说明：
移动端阅览
XIAO Wei, ZHOU Dong-hui, SUN Jian-feng, et al. Implementation of Optimal Weights Initialization Technology in Robot Learning[J]. Acta Electronica Sinica, 2005, 33(9): 1720-1722.
DOI：

XIAO Wei, ZHOU Dong-hui, SUN Jian-feng, et al. Implementation of Optimal Weights Initialization Technology in Robot Learning[J]. Acta Electronica Sinica, 2005, 33(9): 1720-1722. DOI：

摘要

针对移动机器人建立了基于BP神经网络的智能避障控制模型

提出了初始权值优化技术

使得样本组与初始权值相匹配

显著地提高了网络的收敛速度.为了提高系统的实时性

文中采用C和汇编语言混合编制控制程序.计算机仿真和实测结果表明该系统具有学习能力强、人机交互效果好等优点.

Abstract

An intelligent obstacle avoidance model based on BP neural network is established.Also a novel optimal weights initialization technology is proposed so that the sample sets and initial weights can match perfectly.Consequently

the convergence speed increases evidently.In order to improve the real-time performance

hybrid programming using C and assemble language is adopted.Computer simulation and real test show that the system has a strong ability of learning and good performance of human computer interaction.

关键词

Keywords

references

Views

989

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Weight Balance Algorithm of Multilayer Neural Network

The Misadjustment Analysis of BP Algorithm and an Improved Algorithm

A New Algorithm of Multilayer Feedforword Neural Networks Based on Single Parameter Coordinate Rotatory Method

Image Classification Network of Background Perception Mechanism

Related Author

PEI Hao-dong

SU Hong-ye

CHU Jian

WU Wen

LI Xing-guo

JIANG Jin-shui

杨大力

刘泽民

Related Institution

National Lab.of Industrial Process Control,Zhejiang University

Institute of Millimeter Wave and Optical Wave Near Sensing Technique,Nanjing University of Science and Technology

O.Box ,Beijing University of Posts & Telecommuications,Beijing 100088

Harbin Institute of Technology,Department of Computer,Harbin 150001) Feng Yingjun,Wang Xuefeng,Wen Jianhai

哈尔滨工业大学应用数学研究所

⁰